INDEX

Explanations

code-related functions and commands

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InputBorder

-1.00

OrWhiteSpace

-0.94

-0.89

extAlignment

-0.87

posedge

-0.85

BeginContext

-0.81

AnchorStyles

-0.79

BagConstraints

-0.77

脚注の使い方

-0.76

 ―――――

-0.74

POSITIVE LOGITS

RenderAtEndOf

0.82

 function

0.77

Function

0.77

function

0.68

 Function

0.64

isFunction

0.63

Func

0.57

 skill

0.57

callee

0.55

MethodName

0.54

Activations Density 0.559%

code-related functions and commands

No Comments

No Known Activations

code-related functions and commands

No Comments

No Known Activations